{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T09:48:54Z","timestamp":1785923334503,"version":"3.56.0"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819502172","type":"print"},{"value":"9789819502189","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T00:00:00Z","timestamp":1754179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-981-95-0218-9_13","type":"book-chapter","created":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T21:09:18Z","timestamp":1754168958000},"page":"169-180","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Data Debugging Is NP-Hard for\u00a0Classifiers Trained with\u00a0SGD"],"prefix":"10.1007","author":[{"given":"Zizheng","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanzhang","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjing","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"13_CR1","unstructured":"Bae, J., Ng, N., Lo, A., Ghassemi, M., Grosse, R.: If influence functions are the answer, then what is the question? In: Proceedings of the 36th International Conference on Neural Information Processing Systems. NIPS \u201922, Curran Associates Inc., Red Hook, NY (2024)"},{"key":"13_CR2","unstructured":"Basu, S., You, X., Feizi, S.: On second-order group influence functions for black-box predictions. In: Proceedings of the 37th International Conference on Machine Learning. ICML\u201920, JMLR.org (2020)"},{"key":"13_CR3","unstructured":"Brunet, M.E., Alkalay-Houlihan, C., Anderson, A., Zemel, R.: Understanding the origins of bias in word embeddings (2019)"},{"key":"13_CR4","unstructured":"Chang, E., Yeh, H.S., Demberg, V.: Does the order of training samples matter? improving neural data-to-text generation with curriculum learning. ArXiv abs\/2102.03554 (2021). https:\/\/api.semanticscholar.org\/CorpusID:231846815"},{"key":"13_CR5","unstructured":"Demaine, E.D., Gasarch, W., Hajiaghayi, M.: Computational Intractability: A Guide to Algorithmic Lower Bounds. MIT Press (2024)"},{"key":"13_CR6","doi-asserted-by":"crossref","unstructured":"Deng, X., Papadimitriou, C.H.: On the complexity of cooperative solution concepts. Math. Oper. Res. 19, 257\u2013266 (1994).https:\/\/api.semanticscholar.org\/CorpusID:12946448","DOI":"10.1287\/moor.19.2.257"},{"key":"13_CR7","unstructured":"Ghorbani, A., Zou, J.Y.: Data shapley: Equitable valuation of data for machine learning. ArXiv abs\/1904.02868 (2019). https:\/\/api.semanticscholar.org\/CorpusID:102350503"},{"key":"13_CR8","doi-asserted-by":"publisher","unstructured":"Guo, H., Rajani, N., Hase, P., Bansal, M., Xiong, C.: FastIF: Scalable influence functions for efficient model interpretation and debugging. In: Moens, M.F., Huang, X., Specia, L., Yih, S.W.t. (eds.) Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 10333\u201310350. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.808, https:\/\/aclanthology.org\/2021.emnlp-main.808","DOI":"10.18653\/v1\/2021.emnlp-main.808"},{"key":"13_CR9","unstructured":"Hara, S., Nitanda, A., Maehara, T.: Data Cleansing for Models Trained with SGD. Curran Associates Inc., Red Hook, NY (2019)"},{"key":"13_CR10","doi-asserted-by":"crossref","unstructured":"Jacovi, A., Goldberg, Y.: Towards faithfully interpretable NLP systems: How should we define and evaluate faithfulness? In: Annual Meeting of the Association for Computational Linguistics (2020). https:\/\/api.semanticscholar.org\/CorpusID:215416110","DOI":"10.18653\/v1\/2020.acl-main.386"},{"key":"13_CR11","unstructured":"Jia, R., et al.: Towards efficient data valuation based on the shapley value. ArXiv abs\/1902.10275 (2019). https:\/\/api.semanticscholar.org\/CorpusID:67855573"},{"key":"13_CR12","doi-asserted-by":"publisher","unstructured":"Jia, R., et al.: Efficient task-specific data valuation for nearest neighbor algorithms. Proc. VLDB Endow. 12(11), 1610\u20131623 (2019).https:\/\/doi.org\/10.14778\/3342263.3342637","DOI":"10.14778\/3342263.3342637"},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"Jia, R., et al.: Scalability vs. utility: Do we have to sacrifice one for the other in data importance quantification? In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8235\u20138243 (2021).https:\/\/doi.org\/10.1109\/CVPR46437.2021.00814","DOI":"10.1109\/CVPR46437.2021.00814"},{"key":"13_CR14","unstructured":"Karla\u0161, B., et al.: Data debugging with shapley importance over end-to-end machine learning pipelines (2022)"},{"key":"13_CR15","unstructured":"Khanna, R., Kim, B., Ghosh, J., Koyejo, O.: Interpreting black box predictions using fisher kernels. In: International Conference on Artificial Intelligence and Statistics (2018). https:\/\/api.semanticscholar.org\/CorpusID:53085397"},{"key":"13_CR16","unstructured":"Koh, P.W., Ang, K.S., Teo, H.H.K., Liang, P.: On the accuracy of influence functions for measuring group effects. In: Neural Information Processing Systems (2019). https:\/\/api.semanticscholar.org\/CorpusID:173188850"},{"key":"13_CR17","unstructured":"Koh, P.W., Liang, P.: Understanding black-box predictions via influence functions. In: Proceedings of the 34th International Conference on Machine Learning - Volume 70, pp. 1885\u20131894. ICML\u201917, JMLR.org (2017)"},{"key":"13_CR18","doi-asserted-by":"publisher","unstructured":"Li, P., Rao, X., Blase, J., Zhang, Y., Chu, X., Zhang, C.: CleanML: A study for evaluating the impact of data cleaning on ml classification tasks. In: 2021 IEEE 37th International Conference on Data Engineering (ICDE), pp. 13\u201324 (2021).https:\/\/doi.org\/10.1109\/ICDE51399.2021.00009","DOI":"10.1109\/ICDE51399.2021.00009"},{"key":"13_CR19","doi-asserted-by":"publisher","unstructured":"Liu, Y., Wu, W., Flokas, L., Wang, J., Wu, E.: Enabling SQL-based training data debugging for federated learning. In: Proceedings of the VLDB Endowment, Vol.15,pp. 388\u2013400 (2022).https:\/\/doi.org\/10.14778\/3494124.3494125","DOI":"10.14778\/3494124.3494125"},{"key":"13_CR20","doi-asserted-by":"publisher","unstructured":"Mange, J.: Effect of training data order for machine learning. In: 2019 International Conference on Computational Science and Computational Intelligence (CSCI), pp. 406\u2013407 (2019).https:\/\/doi.org\/10.1109\/CSCI49370.2019.00078","DOI":"10.1109\/CSCI49370.2019.00078"},{"key":"13_CR21","unstructured":"Neutatz, F., Chen, B., Abedjan, Z., Wu, E.: From cleaning before ml to cleaning for ml. IEEE Data Eng. Bull. 44, 24\u201341 (2021). https:\/\/api.semanticscholar.org\/CorpusID:237542697"},{"key":"13_CR22","doi-asserted-by":"publisher","unstructured":"Pradhan, R., Zhu, J., Glavic, B., Salimi, B.: Interpretable data-based explanations for fairness debugging. In: Proceedings of the 2022 International Conference on Management of Data. p. 247\u2013261. SIGMOD \u201922, Association for Computing Machinery, New York, NY (2022).https:\/\/doi.org\/10.1145\/3514221.3517886","DOI":"10.1145\/3514221.3517886"},{"key":"13_CR23","unstructured":"Wang, H., Ustun, B., Calmon, F.P.: Repairing without retraining: Avoiding disparate impact with counterfactual distributions (2019)"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Wang, Q., Ma, Y., Zhao, K., Tian, Y.: A Comprehensive Survey of Loss Functions in Machine Learning. Annals of Data Science,pp. 1\u201326 (2020). https:\/\/doi.org\/10.1007\/s40745-020-00253-5","DOI":"10.1007\/s40745-020-00253-5"},{"key":"13_CR25","doi-asserted-by":"publisher","unstructured":"Wu, W., Flokas, L., Wu, E., Wang, J.: Complaint-driven training data debugging for query 2.0, pp. 1317\u20131334 (2020).https:\/\/doi.org\/10.1145\/3318464.3389696","DOI":"10.1145\/3318464.3389696"}],"container-title":["Lecture Notes in Computer Science","Computing and Combinatorics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0218-9_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T09:40:46Z","timestamp":1785922846000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0218-9_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"ISBN":["9789819502172","9789819502189"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0218-9_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"3 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COCOON","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Computing and Combinatorics Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chengdu","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cocoon0","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tcsuestc.com\/cocoon2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}